Moving least square method in learning theory英文文献.pdfVIP

Journal of Approximation Theory 162 (2010) 599–614 /locate/jat Moving least-square method in learning theory a b, c Hong-Yan Wang , Dao-Hong Xiang , Ding-Xuan Zhou a School of Statistics and Mathematics, Zhejiang Gongshang University, Hangzhou, Zhejiang 310018, China b Department of Mathematics, Chinese University of Hong Kong, Shatin, N. T., Hong Kong, China c Department of Mathematics, City University of Hong Kong, Tat Chee Avenue, Kowloon, Hong Kong, China Received 15 March 2009; received in revised form 11 November 2009; accepted 14 December 2009 Available online 23 December 2009 Communicated by Martin Buhmann Abstract Moving least-square (MLS) is an approximation method for data interpolation, numerical analysis and statistics. In this paper we consider the MLS method in learning theory for the regression problem. Essential differences between MLS and other common learning algorithms are pointed out: lack of a natural uniform bound for estimators and the pointwise definition. The sample error is estimated in terms of the weight function and the finite dimensional hypothesis space. The approximation error is dealt with for two special cases for which convergence rates for the total L 2 error measuring the global approximation on the whole domain are provided. c 2009 Elsevier Inc. All rights reserved. Keywords: Learning theory; Moving least-square method; Sample error; Norming condition; Approximation error 1. Introduction Moving least-square method (MLS) is an approximation method for data smoothing [8], numerical analysis [ 10], stat